Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 87 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0414. Min Act: -0.0004

Data Index: 1249402 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0374. Min Act: -0.0004

Data Index: 1006327 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0408. Min Act: -0.0004

Data Index: 619949 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0347. Min Act: -0.0004

Data Index: 1280425 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0348. Min Act: -0.0004

Data Index: 665617 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0343. Min Act: -0.0004

Data Index: 771318 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0319. Min Act: -0.0004

Data Index: 1358487 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0304. Min Act: -0.0004

Data Index: 449738 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0317. Min Act: -0.0004

Data Index: 458448 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0307. Min Act: -0.0004

Data Index: 360297 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0319. Min Act: -0.0004

Data Index: 496251 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0299. Min Act: -0.0004

Data Index: 27644 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0324. Min Act: -0.0004

Data Index: 169384 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0319. Min Act: -0.0004

Data Index: 598178 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0330. Min Act: -0.0004

Data Index: 739937 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0316. Min Act: -0.0004

Data Index: 245655 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0329. Min Act: -0.0004

Data Index: 217878 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0322. Min Act: -0.0004

Data Index: 610941 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0308. Min Act: -0.0004

Data Index: 446563 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0301. Min Act: -0.0004

Data Index: 46284 (C4 (Web Text))

Max Activating Token Index: 22